Evaluating Climate and Community Health Care Infection Risks through Computational Predesign

Abstract

This study highlights the value of computational modeling in health care infection prevention planning, especially in response to climate-induced community risk factors. It investigates the relationship between Socioecological Modeling features and Principal Component Analysis derived parameters in a Decision Tree classification model, predicting regional risk levels of Clostridioides difficile Infection (CDI) and Methicillin-resistant Staphylococcus aureus health care-associated infections (MRSA) Hospital Acquired Infections (HAI). The research confirms that climate-related factors, such as housing instability and medical infrastructure strain, impact regional infectivity risks, influencing health care environment resilience. It emphasizes the link between Clostridioides difficile and MRSA HAI, highlighting the role of Built Environment Vulnerability. These findings have vital implications for hospital predesign, material selection, layout, and hand sanitization device choices, and underscore optimizing patient flow in health care environment planning.